Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.22 +/- 0.10
+      value: -1.16 +/- 1.88
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48a5a5b26179a976bf845553bfd5f306cac0033421475b7ef3416225154ec7c6
+oid sha256:153d38d275560a62556a7715f26ba0ccb80b543fe4721c10d64ac1c8c1a2da63
 size 108089

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2185582671314478, "std_reward": 0.10451684620604006, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-23T17:19:21.296295"}
+{"mean_reward": -1.1598992919549347, "std_reward": 1.8807957399412987, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-23T17:20:03.260613"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2a1727e261854ce898191eb2b28b31f2f2c21d5f0b7a99b87071776bb89a7c3
+oid sha256:583c04d942c5df248bae16dcf01b04c57f23d0764518680f8d70e4ec11874b69
 size 2636